Start Building Your Agentforce Agents Today!<\/h2>\n\t\t\t\t\t\t\t
Unlock the full potential of Agentforce by learning to define roles, extend capabilities with advanced tools, and customise to fit your business needs. Sign up for our demos now!<\/p>\n\t\t\t\n\t\t\t\n\t\t\t\t\t\t\t
![\"\"](\"https:\/\/www.salesforce.com\/eu\/blog\/wp-content\/uploads\/sites\/14\/2024\/10\/agentforce-form-conf-og-image.png\")
\t\t<\/div>\n\t<\/div>\n\n\t\n\t<\/div>\n\n\n\nWhen chatbots or agents try too hard to sound human, it can backfire. Imagine asking a serious question about your bank account or a medical test, and the agent responds very conversationally, with empathetic language. You may be led to believe it\u2019s a real person, and when you realise it\u2019s actually a piece of technology, feel frustrated and lose trust. Do you want real answers or AI pretending to be your new best friend?<\/p>\n\n\n\n
Businesses need to consider a range of guidelines when building an agent. They may sound human, but that doesn\u2019t mean they should take on human characteristics, too. UX designers need to consider how to help users clearly distinguish between digital agents and humans, addressing questions like: Should they have a name or use pronouns? Should they be represented by an avatar or even a real person? Should they be able to understand and respond to emotional cues? <\/p>\n\n\n\n
Yvonne Gando, senior director of UX at Salesforce, said businesses might be tempted to make the agent more relatable by giving it human traits. She encourages businesses to focus on competence over personality, and stresses the importance of maintaining the distinction between human and AI.<\/p>\n\n\n\n
Agents should boost human potential, not pretend to be a \u201cdigital human.\u201d Why? Giving an AI agent human-like qualities sets users up for unrealistic expectations. It can\u2019t actually empathise or understand emotions. Plus, when we blur the line between human and machine, people may develop unnecessary emotional attachments or start leaning on agents in ways that could lead to ethical problems or misuse.<\/p>\n\n\n\n
\u201cFocus on what the user needs, not the AI doing it,\u201d Gando said. <\/p>\n\n\n\n
Here are some suggested design principles for AI agents. <\/p>\n\n\n\n
AI agent design principle #1: Focus on the work, not the agent doing the work <\/h2>\n\n\n\n
The agent\u2019s job is to carry out tasks \u2014 to free up workers so they can tackle more complex issues and be more productive and efficient. The focus, then, should be on the tasks, activities, and outcomes a user can achieve through the agent, rather than the agent itself. Before deciding to give your agent a gender or other human trait, ask yourself if it\u2019s a requirement for the agent to carry out the task. This helps you focus on the user\u2019s needs. <\/p>\n\n\n\n
\u201cWhen AI agents are given human-like personalities, users may begin to relate to them as they would to a person,\u201d said Gando. \u201cIf the agent can\u2019t meet those expectations or misunderstands a question, this often leads to disappointment and a loss of trust in the brand. It\u2019s more effective to keep AI interactions helpful and approachable without creating a false sense of human connection.\u201d<\/p>\n\n\n\n
Avoid giving agents pronouns, because it could be construed as giving it equal weight to a human worker. Instead of an agent saying, \u201cI wanted to give you these documents,\u201d consider \u201cHere are documents you might find helpful.\u201d<\/p>\n\n\n\n
AI agent design principle #2: Always identify agents as such <\/h2>\n\n\n\n
AI agents are becoming so adept at communicating in natural language that it can be hard to know whether you\u2019re talking with a person or a piece of technology. Three states \u2014 California, Utah, and Colorado \u2014 have enacted laws<\/a> requiring bot use disclosure in certain circumstances. Mandates aside, the best practice is to immediately identify the use of AI with any customer interaction.\u00a0<\/p>\n\n\n\n \u201cYou should always start a conversation knowing that the entity you\u2019re interacting with is AI,\u201d said Gando. \u201cThere is a real loss of trust and transparency when the customer doesn\u2019t know.\u201d<\/p>\n\n\n\n Salesforce\u2019s Agentforce<\/a>, by default, alerts administrators<\/a> and agent managers when they\u2019re about to implement or use AI agents. Disclosures make sure the recipients of agent-generated emails know they were created and executed by AI. A nonremovable and non-editable disclaimer below the signature line adds extra transparency.<\/p>\n\n\n\n If an agent is stumped by a request or has outrun what it\u2019s been programmed to do, it should do a smooth handoff to a human. In that situation, the agent should clearly alert the customer to the transfer. <\/p>\n\n\n\n Einstein Service Agent<\/a>, for example, automatically escalates more complicated service calls or questions to humans based on the parameters set by the company.<\/p>\n\n\n\nAI agent design principle #3: Maintain a clear distinction between human and digital workers<\/h2>\n\n\n\n